TokenLab MCP Server

Create multimodal embeddings

create_multimodal_embedding

Generate vector embeddings from text or image inputs for multimodal search, clustering, and similarity tasks. Text works generally; image support may require feature enablement.

Instructions

Creates embeddings for multimodal input items. Text input is generally available; image input may require feature enablement.

Input Schema

TableJSON Schema

Name	Required	Description
`input`	Yes
`model`	Yes	Model to use for multimodal embeddings
`dimensions`	No	Optional embedding dimensionality when supported by the selected model
`X-TokenLab-Delivery-Policy`	No	Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri…

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.6.24Oct 2, 2026

addedInput schema / properties / X-TokenLab-Delivery-Policy

Added value: +{
+  "description": "Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri…",
+  "enum": [
+    "auto",
+    "verified",
+    "official"
+  ],
+  "type": "string"
+}

changedInput schema / properties / input / oneOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "description": "A multimodal embedding input item. Text input is generally available; image input may require feature enablement.",
-    "properties": {
-      "image_base64": {
-        "description": "Base64-encoded image content",
-        "type": "string"
-      },
-      "image_mime_type": {
-        "description": "MIME type for image_base64",
-        "type": "string"
-      },
-      "image_url": {
-        "description": "Public image URL to embed",
-        "type": "string"
-      },
-      "text": {
-        "description": "Text to embed",
-        "type": "string"
-      }
-    },
-    "type": "object"
-  },
-  {
-    "items": {
-      "description": "A multimodal embedding input item. Text input is generally available; image input may require feature enablement.",
-      "type": "object"
-    },
-    "minItems": 1,
-    "type": "array"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "description": "A multimodal embedding input item. Text input is generally available; image input may require featu…",
+    "properties": {
+      "image_base64": {
+        "description": "Base64-encoded image content",
+        "type": "string"
+      },
+      "image_mime_type": {
+        "description": "MIME type for image_base64",
+        "type": "string"
+      },
+      "image_url": {
+        "description": "Public image URL to embed",
+        "type": "string"
+      },
+      "text": {
+        "description": "Text to embed",
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "items": {
+      "description": "A multimodal embedding input item. Text input is generally available; image input may require featu…",
+      "type": "object"
+    },
+    "minItems": 1,
+    "type": "array"
+  }
+]

Changed3 schema fields changedv0.6.4Jul 25, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedInput schema / properties / dimensions / maximum
```
Removed value: -9007199254740991
```

changedInput schema / properties / input / oneOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "description": "A multimodal embedding input item. Text input is generally available; image input may require feature enablement.",
-    "properties": {
-      "image_base64": {
-        "description": "Base64-encoded image content",
-        "type": "string"
-      },
-      "image_mime_type": {
-        "description": "MIME type for image_base64",
-        "type": "string"
-      },
-      "image_url": {
-        "description": "Public image URL to embed",
-        "type": "string"
-      },
-      "text": {
-        "description": "Text to embed",
-        "type": "string"
-      }
-    },
-    "type": "object"
-  },
-  {
-    "items": {
-      "additionalProperties": false,
-      "description": "A multimodal embedding input item. Text input is generally available; image input may require feature enablement.",
-      "properties": {
-        "image_base64": {
-          "description": "Base64-encoded image content",
-          "type": "string"
-        },
-        "image_mime_type": {
-          "description": "MIME type for image_base64",
-          "type": "string"
-        },
-        "image_url": {
-          "description": "Public image URL to embed",
-          "type": "string"
-        },
-        "text": {
-          "description": "Text to embed",
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "minItems": 1,
-    "type": "array"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "description": "A multimodal embedding input item. Text input is generally available; image input may require feature enablement.",
+    "properties": {
+      "image_base64": {
+        "description": "Base64-encoded image content",
+        "type": "string"
+      },
+      "image_mime_type": {
+        "description": "MIME type for image_base64",
+        "type": "string"
+      },
+      "image_url": {
+        "description": "Public image URL to embed",
+        "type": "string"
+      },
+      "text": {
+        "description": "Text to embed",
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "items": {
+      "description": "A multimodal embedding input item. Text input is generally available; image input may require feature enablement.",
+      "type": "object"
+    },
+    "minItems": 1,
+    "type": "array"
+  }
+]

Addedv0.3.1Jul 10, 2026

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds genuinely useful context beyond them: text input is generally available while image input may require feature enablement, a real prerequisite. It says nothing about cost, rate limits, or return format, so with annotations covering safety a 3 fits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler, with the core action stated first and the availability caveat second. Nothing redundant, though it is very terse given the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description should ideally describe what is returned (embedding vectors and their shape), which it does not. The feature-enablement note is a helpful prerequisite, but the agent still lacks return-value context for an embedding tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75% across 4 parameters, and the description adds no syntax or format detail beyond what the schema documents. Its only parameter-adjacent contribution is the feature-enablement caveat for image inputs, which the schema does not convey. Baseline 3 is appropriate given the schema does most of the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (creates), resource (embeddings), and scope (multimodal input items), which distinguishes it from the sibling create_embedding by implying combined text/image input. It stops short of explicitly naming that sibling, so the differentiation is implied rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is only implied: the multimodal framing suggests using this when image input is involved, and it notes image input may require feature enablement. There is no explicit when-to-use versus create_embedding or rerank_documents, and no stated alternative selection rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Create multimodal embeddings

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools